Evolving Morphologies for Locomoting Micro-scale Robotic Agents

Matthew Uppington; Helmut Hauser; Sabine Hauert; Pierangelo Gobbo

doi:10.1109/MARSS55884.2022.9870459

Evolving Morphologies for Locomoting Micro-scale Robotic Agents

Matthew Uppington, Helmut Hauser, Sabine Hauert, Pierangelo Gobbo

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

1 Citation (Scopus)

102 Downloads (Pure)

Abstract

Designing new locomotive mechanisms for micro-scale robotic systems could enable new approaches to tackling problems such as transporting cargos, or self-assembling in to pre-programmed architectures. Morphological factors often play a crucial role in determining the behaviour of microsystems, yet understanding how to design these aspects optimally is a challenge. This paper explores how the morphology of a multi-cellular micro-robotic agent can be optimised for reliable locomotion using artificial evolution in a stochastic simulator. Evolved morphologies are found to yield significantly better performance in terms of the reliability of the travel direction and the distance covered, compared to random morphologies.

Original language	English
Title of host publication	Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales
Editors	Sinan Haliyo, Mokrane Boudaoud, Eric Diller, Xinyu Liu, Yu Sun, Sergej Fatikow
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	5
ISBN (Electronic)	9781665459730
ISBN (Print)	9781665459747
DOIs	https://doi.org/10.1109/MARSS55884.2022.9870459
Publication status	E-pub ahead of print - 2 Sept 2022
Event	MARSS 2022 Conference - University of Toronto, Toronto, Canada Duration: 25 Jul 2022 → 29 Jul 2022 Conference number: 55884X https://marss-conference.org/

Publication series

Name	Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales
ISSN (Print)	2194-6426
ISSN (Electronic)	2194-6418

Conference

Conference	MARSS 2022 Conference
Country/Territory	Canada
City	Toronto
Period	25/07/22 → 29/07/22
Internet address	https://marss-conference.org/

Bibliographical note

Funding Information:
This work is supported by the EPSRC Robotics and Autonomous Systems Centre for Doctoral Training (FARSCOPE) (UKRI Grant No. EP/S021795/1) (M.U).

Publisher Copyright:
© 2022 IEEE.

Access to Document

10.1109/MARSS55884.2022.9870459

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/9870459. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 611 KB

Handle.net

Persistent link

Cite this

Uppington, M., Hauser, H., Hauert, S., & Gobbo, P. (2022). Evolving Morphologies for Locomoting Micro-scale Robotic Agents. In S. Haliyo, M. Boudaoud, E. Diller, X. Liu, Y. Sun, & S. Fatikow (Eds.), Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales (Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales). Institute of Electrical and Electronics Engineers (IEEE). Advance online publication. https://doi.org/10.1109/MARSS55884.2022.9870459

Uppington, Matthew ; Hauser, Helmut ; Hauert, Sabine et al. / Evolving Morphologies for Locomoting Micro-scale Robotic Agents. Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales. editor / Sinan Haliyo ; Mokrane Boudaoud ; Eric Diller ; Xinyu Liu ; Yu Sun ; Sergej Fatikow. Institute of Electrical and Electronics Engineers (IEEE), 2022. (Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales).

@inproceedings{a06d3570ec7744efa35dfd2767488fbc,

title = "Evolving Morphologies for Locomoting Micro-scale Robotic Agents",

abstract = "Designing new locomotive mechanisms for micro-scale robotic systems could enable new approaches to tackling problems such as transporting cargos, or self-assembling in to pre-programmed architectures. Morphological factors often play a crucial role in determining the behaviour of microsystems, yet understanding how to design these aspects optimally is a challenge. This paper explores how the morphology of a multi-cellular micro-robotic agent can be optimised for reliable locomotion using artificial evolution in a stochastic simulator. Evolved morphologies are found to yield significantly better performance in terms of the reliability of the travel direction and the distance covered, compared to random morphologies.",

author = "Matthew Uppington and Helmut Hauser and Sabine Hauert and Pierangelo Gobbo",

note = "Funding Information: This work is supported by the EPSRC Robotics and Autonomous Systems Centre for Doctoral Training (FARSCOPE) (UKRI Grant No. EP/S021795/1) (M.U). Publisher Copyright: {\textcopyright} 2022 IEEE.; MARSS 2022 Conference ; Conference date: 25-07-2022 Through 29-07-2022",

year = "2022",

month = sep,

day = "2",

doi = "10.1109/MARSS55884.2022.9870459",

language = "English",

isbn = "9781665459747",

series = "Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

editor = "Sinan Haliyo and Mokrane Boudaoud and Eric Diller and Xinyu Liu and Yu Sun and Sergej Fatikow",

booktitle = "Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales",

address = "United States",

url = "https://marss-conference.org/",

}

Uppington, M, Hauser, H , Hauert, S & Gobbo, P 2022, Evolving Morphologies for Locomoting Micro-scale Robotic Agents. in S Haliyo, M Boudaoud, E Diller, X Liu, Y Sun & S Fatikow (eds), Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales. Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales, Institute of Electrical and Electronics Engineers (IEEE), MARSS 2022 Conference, Toronto, Canada, 25/07/22. https://doi.org/10.1109/MARSS55884.2022.9870459

Evolving Morphologies for Locomoting Micro-scale Robotic Agents. / Uppington, Matthew; Hauser, Helmut ; Hauert, Sabine et al.
Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales. ed. / Sinan Haliyo; Mokrane Boudaoud; Eric Diller; Xinyu Liu; Yu Sun; Sergej Fatikow. Institute of Electrical and Electronics Engineers (IEEE), 2022. (Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Evolving Morphologies for Locomoting Micro-scale Robotic Agents

AU - Uppington, Matthew

AU - Hauser, Helmut

AU - Hauert, Sabine

AU - Gobbo, Pierangelo

N1 - Conference code: 55884X

PY - 2022/9/2

Y1 - 2022/9/2

N2 - Designing new locomotive mechanisms for micro-scale robotic systems could enable new approaches to tackling problems such as transporting cargos, or self-assembling in to pre-programmed architectures. Morphological factors often play a crucial role in determining the behaviour of microsystems, yet understanding how to design these aspects optimally is a challenge. This paper explores how the morphology of a multi-cellular micro-robotic agent can be optimised for reliable locomotion using artificial evolution in a stochastic simulator. Evolved morphologies are found to yield significantly better performance in terms of the reliability of the travel direction and the distance covered, compared to random morphologies.

AB - Designing new locomotive mechanisms for micro-scale robotic systems could enable new approaches to tackling problems such as transporting cargos, or self-assembling in to pre-programmed architectures. Morphological factors often play a crucial role in determining the behaviour of microsystems, yet understanding how to design these aspects optimally is a challenge. This paper explores how the morphology of a multi-cellular micro-robotic agent can be optimised for reliable locomotion using artificial evolution in a stochastic simulator. Evolved morphologies are found to yield significantly better performance in terms of the reliability of the travel direction and the distance covered, compared to random morphologies.

U2 - 10.1109/MARSS55884.2022.9870459

DO - 10.1109/MARSS55884.2022.9870459

M3 - Conference Contribution (Conference Proceeding)

SN - 9781665459747

T3 - Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales

BT - Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales

A2 - Haliyo, Sinan

A2 - Boudaoud, Mokrane

A2 - Diller, Eric

A2 - Liu, Xinyu

A2 - Sun, Yu

A2 - Fatikow, Sergej

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - MARSS 2022 Conference

Y2 - 25 July 2022 through 29 July 2022

ER -

Uppington M, Hauser H , Hauert S, Gobbo P. Evolving Morphologies for Locomoting Micro-scale Robotic Agents. In Haliyo S, Boudaoud M, Diller E, Liu X, Sun Y, Fatikow S, editors, Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales. Institute of Electrical and Electronics Engineers (IEEE). 2022. (Proceedings of MARSS 2022 - 5th International Conference on Manipulation, Automation, and Robotics at Small Scales). Epub 2022 Sept 2. doi: 10.1109/MARSS55884.2022.9870459

Evolving Morphologies for Locomoting Micro-scale Robotic Agents

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this